Triple
T8962510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anthony Frederick Augustus Sandys |
E214041
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Perdita |
E409793
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Perdita | Statement: [Anthony Frederick Augustus Sandys, notableWork, Perdita]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perdita Context triple: [Anthony Frederick Augustus Sandys, notableWork, Perdita]
-
A.
Perdita
Perdita is the gentle and devoted mother Dalmatian in Disney's "One Hundred and One Dalmatians," known for her bravery and determination to protect her puppies.
-
B.
Perdita
chosen
Perdita is a central character in Shakespeare’s play "The Winter’s Tale," known as the lost princess who is raised by shepherds and later restores harmony between estranged royal families.
-
C.
Aemilia
Aemilia was a prominent Dutch warship that served as the flagship of the Dutch fleet during the Battle of the Downs in 1639.
-
D.
Marcellina
Marcellina is a small Italian municipality in the Lazio region, situated near Rome in the province of Rome.
-
E.
Athenodora
Athenodora is a vampire in the Twilight series, known as one of the ancient female leaders of the Volturi coven.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca839cd6008190a1546a701a56710c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6749e5008190a01f42a2e772dd54 |
completed | April 1, 2026, 12:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc94e088881909506b229d1fff44a |
completed | April 3, 2026, 2:06 p.m. |
Created at: March 30, 2026, 7:01 p.m.